In this work, we demonstrate an over-the-air communications system which is solely based on deep neural networks and has, thus far, only been validated by computer simulations for block-based transmissions. Transmitter and receiver can be jointly trained end-to-end for an arbitrary differentiable end-to-end performance metric, e.g., block error rate (BLER). We demonstrate that it is possible to build and train such a system using off-the-shelf software-defined radios (SDRs) and open-source deep learning software libraries. A comparison of the BLER performance of the "learned" system against that of a practical baseline shows competitive performance. We identify several practical challenges of training such a system over-the-air, in particular the missing channel gradient, and propose a learning procedure that circumvents this issue.
%0 Conference Paper
%1 learning_to_communicate_asilomar
%A Dörner, Sebastian
%A Cammerer, Sebastian
%A Hoydis, Jakob
%A ten Brink, Stephan
%B 2017 51st Asilomar Conference on Signals, Systems, and Computers
%D 2017
%K myown from:sdnr autoencoder ml
%P 1791-1795
%R 10.1109/ACSSC.2017.8335670
%T On deep learning-based communication over the air
%U https://ieeexplore.ieee.org/document/8335670
%X In this work, we demonstrate an over-the-air communications system which is solely based on deep neural networks and has, thus far, only been validated by computer simulations for block-based transmissions. Transmitter and receiver can be jointly trained end-to-end for an arbitrary differentiable end-to-end performance metric, e.g., block error rate (BLER). We demonstrate that it is possible to build and train such a system using off-the-shelf software-defined radios (SDRs) and open-source deep learning software libraries. A comparison of the BLER performance of the "learned" system against that of a practical baseline shows competitive performance. We identify several practical challenges of training such a system over-the-air, in particular the missing channel gradient, and propose a learning procedure that circumvents this issue.
@inproceedings{learning_to_communicate_asilomar,
abstract = {In this work, we demonstrate an over-the-air communications system which is solely based on deep neural networks and has, thus far, only been validated by computer simulations for block-based transmissions. Transmitter and receiver can be jointly trained end-to-end for an arbitrary differentiable end-to-end performance metric, e.g., block error rate (BLER). We demonstrate that it is possible to build and train such a system using off-the-shelf software-defined radios (SDRs) and open-source deep learning software libraries. A comparison of the BLER performance of the "learned" system against that of a practical baseline shows competitive performance. We identify several practical challenges of training such a system over-the-air, in particular the missing channel gradient, and propose a learning procedure that circumvents this issue.},
added-at = {2022-03-22T12:29:36.000+0100},
author = {{D\"orner}, Sebastian and {Cammerer}, Sebastian and {Hoydis}, Jakob and {ten Brink}, Stephan},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/28cbbbeec1351229729602e36ceb32e90/inue},
booktitle = {2017 51st Asilomar Conference on Signals, Systems, and Computers},
doi = {10.1109/ACSSC.2017.8335670},
interhash = {27fb5d7678ffd0a48b4e3c9372f516b4},
intrahash = {8cbbbeec1351229729602e36ceb32e90},
issn = {2576-2303},
keywords = {myown from:sdnr autoencoder ml},
month = oct,
pages = {1791-1795},
timestamp = {2022-03-22T11:29:36.000+0100},
title = {On deep learning-based communication over the air},
url = {https://ieeexplore.ieee.org/document/8335670},
year = 2017
}
